Interdisciplinary Sciences: Computational Life Sciences ( IF 3.9 ) Pub Date : 2021-07-05 , DOI: 10.1007/s12539-021-00450-7 Xiaoxiao Chen 1 , Linghui Li 1 , Ashutosh Sharma 2 , Gaurav Dhiman 3 , S Vimal 4
|
The disease Alzheimer is an irrepressible neurologicalbrain disorder. Earlier detection and proper treatment of Alzheimer’s disease can help for brain tissue damage prevention. The study was intended to explore the segmentation effects of convolutional neural network (CNN) model on Magnetic Resonance (MR) imaging for Alzheimer's diagnosis and nursing. Specifically, 18 Alzheimer's patients admitted to Indira Gandhi Medical College (IGMC) hospital were selected as the experimental group, with 18 healthy volunteers in the Ctrl group. Furthermore, the CNN model was applied to segment the MR imaging of Alzheimer's patients, and its segmentation effects were compared with those of the fully convolutional neural network (FCNN) and support vector machine (SVM) algorithms. It was found that the CNN model demonstrated higher segmentation precision, and the experimental group showed a higher clinical dementia rating (CDR) score and a lower mini-mental state examination (MMSE) score (P < 0.05). The size of parahippocompalgyrus and putamen was bigger in the Ctrl (P < 0.05). In experimental group, the amplitude of low-frequency fluctuation (ALFF) was positively correlated with the MMSE score in areas of bilateral cingulum gyri (r = 0.65) and precuneus (r = 0.59). In conclusion, the grey matter structure is damaged in Alzheimer's patients, and hippocampus ALFF and regional homogeneity (ReHo) is involved in the neuronal compensation mechanism of hippocampal damage, and the caregivers should take an active nursing method.
Graphic abstract
中文翻译：
卷积神经网络模型在阿尔茨海默病MR影像诊断与护理中的应用
阿尔茨海默病是一种无法抑制的神经性脑病。早期发现和适当治疗阿尔茨海默病有助于预防脑组织损伤。本研究旨在探讨卷积神经网络 (CNN) 模型对阿尔茨海默病诊断和护理的磁共振 (MR) 成像的分割效果。具体而言，选择英迪拉甘地医学院（IGMC）医院收治的18名阿尔茨海默病患者作为实验组，其中18名健康志愿者为Ctrl组。此外，将CNN模型应用于阿尔茨海默病患者的MR图像分割，并将其分割效果与全卷积神经网络（FCNN）和支持向量机（SVM）算法的分割效果进行了比较。P < 0.05)。Ctrl组海马旁和壳核体积较大( P < 0.05)。实验组双侧扣带回区（ r =0.65）和楔前叶区（r =0.59）的低频波动幅度（ALFF）与MMSE评分呈正相关。综上所述，阿尔茨海默病患者灰质结构受损，海马ALFF和区域同质性（ReHo）参与了海马损伤的神经元代偿机制，护理人员应采取积极的护理方法。
京公网安备 11010802027423号